The edge of chaos: quantum field theory and deep neural networks

D. Gilboa, B. Chang, M. Chen, G. Yang, S. S. Schoenholz, E. H. Chi, and J. Pennington, “Dynamical isometry and a mean field theory of lstms and grus,” arXiv:1901.08987 [cs.LG]

Original

1901

Earlier work this paper cites.

M. Helias and D. Dahmen, “Statistical field theory for neural networks,” arXiv:1901.10416 [cond-mat.dis-nn]

Original

1901

Earlier work this paper cites.

J. M. Antognini, “Finite size corrections for neural network gaussian processes,” arXiv:1908.10030 [cs.LG]

Original

1908

Earlier work this paper cites.

E. Dyer and G. Gur-Ari, “Asymptotics of Wide Networks from Feynman Diagrams,” arXiv:1909.11304 [cs.LG]

Original

1909

Earlier work this paper cites.

S. Yaida, “Non-Gaussian processes and neural networks at finite widths,” arXiv:1910.00019 [stat.ML]

Original

1910

Earlier work this paper cites.

D. Chialvo, “Life at the edge: Complexity and criticality in biological function,” Acta Physica Polonica B

1955

Earlier work this paper cites.

R. Price, “A useful theorem for nonlinear devices having gaussian inputs,” IRE Transactions on Information Theory

1958

Earlier work this paper cites.

E. Brezin and D. J. Wallace, “Critical Behavior of a Classical Heisenberg Ferromagnet with many Degrees of Freedom,” Phys. Rev. B

1967

Earlier work this paper cites.

G. ’t Hooft, “A Planar Diagram Theory for Strong Interactions,” Nucl. Phys. B

1974

Earlier work this paper cites.

H. Sompolinsky and A. Zippelius, “Relaxational dynamics of the edwards-anderson model and the mean-field theory of spin-glasses,” Phys. Rev. B

1982

Earlier work this paper cites.

Cambridge University Press, Cambridge, U.K., 1985

S. Coleman, Aspects of Symmetry: Selected Erice Lectures · 1985

Earlier work this paper cites.

H. Sompolinsky, A. Crisanti, and H. J. Sommers, “Chaos in random neural networks,” Phys. Rev. Lett

1988

Earlier work this paper cites.

H. Sompolinsky, A. Crisanti, and H. J. Sommers, “Chaos in random neural networks,” Phys. Rev. Lett

1988

Earlier work this paper cites.

C. G. Langton, “Computation at the edge of chaos: Phase transitions and emergent computation,” Physica D: Nonlinear Phenomena

1990

Earlier work this paper cites.

McGraw-Hill, New York, 4th ed., 1991

A. Papoulis and S. U. Pillai, Probability, Random Variables, and Stochastic Processes · 1991

Cited alongside, same era.

World scientific, 1993

E. Brézin and S. R. Wadia, The large N expansion in quantum field theory and statistical physics · 1993

Cited alongside, same era.

R. M. Neal, “Bayesian learning for neural networks,” PhD thesis, University of Toronto

1995

Cited alongside, same era.

D. R. Chialvo and P. Bak, “Learning from Mistakes,” arXiv e-prints

1997

Cited alongside, same era.

J. M. Maldacena, “The Large N limit of superconformal field theories and supergravity,” Adv. Theor. Math. Phys

1998

Cited alongside, same era.

O. Aharony, S. S. Gubser, J. M. Maldacena, H. Ooguri, and Y. Oz, “Large N field theories, string theory and gravity,” Phys. Rept

2000

J. Beggs and N. Timme, “Being critical of criticality in the brain,” Frontiers in Physiology

2012

Later among the works it cites.

D. R. Chialvo, S. A. Cannas, D. Plenz, and T. S. Grigera, “Controlling a complex system near its critical point via temporal correlations,” 2019

2019

Later among the works it cites.

Y. Bahri, J. Kadmon, J. Pennington, S. S. Schoenholz, J. Sohl-Dickstein, and S. Ganguli, “Statistical mechanics of deep learning,” Annual Review of Condensed Matter Physics

2020

Later among the works it cites.

J. Lee, L. Xiao, S. S. Schoenholz, Y. Bahri, R. Novak, J. Sohl-Dickstein, and J. Pennington, “Wide neural networks of any depth evolve as linear models under gradient descent,” Journal of Statistical Mechanics: Theory and Experiment

2020

Later among the works it cites.

V. Zimmern, “Why brain criticality is clinically relevant: A scoping review,” Frontiers in Neural Circuits